Fully Self-Supervised Class Awareness in Dense Object DescriptorsDownload PDF

19 Jun 2021, 10:04 (modified: 01 Nov 2021, 14:59)CoRL2021 PosterReaders: Everyone
Keywords: Self-Supervision, Descriptor Learning, Object Correspondence
Abstract: We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete labels or confidence in object similarities. We quantitatively and qualitatively show that the introduced method outperforms previous techniques with more robust pixel-to-pixel matches. An example robotic application is also shown~- grasping of objects in clutter based on corresponding points.
Supplementary Material: zip
Poster: png
18 Replies